Claude Introduces Skills to Cut Prompt Hassle
Key Points
- Claude’s new “skills launch” introduces composable “capabilities” (Lego‑brick style markdown files) that can be enabled once and called automatically in any conversation, dramatically reducing prompt‑dependency.
- By storing detailed instructions (e.g., job‑search preferences, site choices, compensation goals) inside a skill, users can simply ask Claude for help and the model will retrieve and apply the appropriate context without re‑prompting.
- This approach streamlines complex, multi‑step tasks such as building resumes, designing PowerPoints, or performing financial analyses, making them accessible to far more people.
- The same markdown‑based skill system can be ported to other AI platforms like ChatGPT and Gemini, extending the efficiency gains beyond Claude.
- Overall, the technique turns arduous, prompt‑heavy workflows into intuitive, low‑effort interactions, marking a major productivity breakthrough for AI‑augmented work.
Sections
- Claude Introduces Composable Skills - The speaker explains Claude’s new “skills launch,” a set of enableable, Lego‑brick‑like capabilities that let users move beyond prompt‑heavy workflows, making complex tasks such as presentations, Excel analyses, and job‑search strategies easier to automate.
- Creating Custom Claude Skills - The speaker explains how users can develop their own Claude skills to simplify complex tasks, contrasting standard built‑in skills with custom ones like a prompting pattern library.
- Composable AI Skills as Lego - The speaker explains how to create reusable, modular instruction files (skills) for LLMs such as GPT, Claude, and Gemini, enabling you to package prompts into “Lego‑brick” components that can be zipped, uploaded, and referenced for consistent task execution.
- Launching Cloud Prompting Toolkit - The speaker announces a soon‑to‑be video and Substack post offering a starter pack for using Claude and other cloud‑based prompting tools, promising users quick access to powerful new prompting capabilities.
Full Transcript
# Claude Introduces Skills to Cut Prompt Hassle **Source:** [https://www.youtube.com/watch?v=UaJhYp7Tql4](https://www.youtube.com/watch?v=UaJhYp7Tql4) **Duration:** 00:12:02 ## Summary - Claude’s new “skills launch” introduces composable “capabilities” (Lego‑brick style markdown files) that can be enabled once and called automatically in any conversation, dramatically reducing prompt‑dependency. - By storing detailed instructions (e.g., job‑search preferences, site choices, compensation goals) inside a skill, users can simply ask Claude for help and the model will retrieve and apply the appropriate context without re‑prompting. - This approach streamlines complex, multi‑step tasks such as building resumes, designing PowerPoints, or performing financial analyses, making them accessible to far more people. - The same markdown‑based skill system can be ported to other AI platforms like ChatGPT and Gemini, extending the efficiency gains beyond Claude. - Overall, the technique turns arduous, prompt‑heavy workflows into intuitive, low‑effort interactions, marking a major productivity breakthrough for AI‑augmented work. ## Sections - [00:00:00](https://www.youtube.com/watch?v=UaJhYp7Tql4&t=0s) **Claude Introduces Composable Skills** - The speaker explains Claude’s new “skills launch,” a set of enableable, Lego‑brick‑like capabilities that let users move beyond prompt‑heavy workflows, making complex tasks such as presentations, Excel analyses, and job‑search strategies easier to automate. - [00:03:19](https://www.youtube.com/watch?v=UaJhYp7Tql4&t=199s) **Creating Custom Claude Skills** - The speaker explains how users can develop their own Claude skills to simplify complex tasks, contrasting standard built‑in skills with custom ones like a prompting pattern library. - [00:07:33](https://www.youtube.com/watch?v=UaJhYp7Tql4&t=453s) **Composable AI Skills as Lego** - The speaker explains how to create reusable, modular instruction files (skills) for LLMs such as GPT, Claude, and Gemini, enabling you to package prompts into “Lego‑brick” components that can be zipped, uploaded, and referenced for consistent task execution. - [00:11:48](https://www.youtube.com/watch?v=UaJhYp7Tql4&t=708s) **Launching Cloud Prompting Toolkit** - The speaker announces a soon‑to‑be video and Substack post offering a starter pack for using Claude and other cloud‑based prompting tools, promising users quick access to powerful new prompting capabilities. ## Full Transcript
I think that this is one of the biggest
pieces of news in the entire year.
Claude launched a way for us to get past
the tyranny of the prompt and I worked
out a way to use that same technique
outside Claude in Chad GPT in Gemini and
other places. We're going to dive into
the whole thing, but the first piece I
want you to realize is that everything
has been prompt dependent and that has
made hard work really difficult.
Basically, if you want to do something
complicated like a PowerPoint or an
Excel or a full financial analysis, it's
possible, but it's really been prompt
dependent. And anything we can do that
makes it slightly easier, slightly less
dependent on the prompt is a really big
deal because it makes it so much easier
for so many more people to do that hard
work. That is what we got today from
Claude. It's called the skills launch.
And the idea is that you have these
composable Lego bricks. They're called
capabilities in your settings section.
I'm going to show you here in a second.
And all you have to do is enable
capabilities that Claude can call in any
conversation in any combination. And so
I'll give you a specific example. One of
the things that has been difficult for
people to do with AI has been a
complicated task like figuring out a job
search strategy. So let's say you need
to identify candidate job postings. You
need to compose a resume that fits those
job postings. You need to make sure that
your search strategy actually works for
those jobs. That your targeting strategy
works for outreach. This is complicated
work. Normally it would take a lot of
prompts. It would take many prompts in a
row. Some people sign up for tools and
services for this. What you can do with
Claude is you can make skills that refer
to this complicated work and give Claude
special instructions to do it well. Like
your job search strategy could instruct
Claude specifically what sites you
prefer, what job family and roles you
prefer, what levels you prefer, what
compensation you want. And all of that
would be stored inside this Lego brick
of context that Claude can go and call.
Not when you have to tag it. You don't
have to remember it. You just have to
say, "Hey, I'm trying to think about
what job search strategy I should use
for this week." And then give it some
context about your last few weeks, your
learnings. Help me figure it out. Claude
will look at that initial prompt,
understand you're talking about job
search, and go dig up a skill and use it
on the fly. It's super intuitive. And
the magical thing is because of the way
they've simplified the the file
structure, the Lego brick, it's just a
markdown file. you can use this other
places and that's what I figured out. So
I'm going to show you that too. You can
use it in Chad GPT in Gemini. And what
this does is it makes the whole process
of doing a difficult complicated
multi-step piece of work so much easier.
And so this is not just a story about
can we make PowerPoints easier, can we
make Excel easier, can we make job
search easier. It's a story about can we
do hard work with much less effort. It's
like Claude gave us a lever, a 10X lever
on our prompting. And so without further
ado, I'm going to jump in. And the first
thing I'm going to show you is sort of
the the settings page, how this actually
looks when you when you sign up for it.
But we won't spend much time there.
We're going to spend most of our time
diving into how you create these because
the magic of this is that you are not
locked in to whatever the Anthropic and
Claude team give you. You can make these
yourself. And I can make them for you.
And I have. I'm making them for you.
It's so exciting because we can
basically make these big packages that
help us to effectively do lots and lots
of complex work. Another example is
vendor AI vendor risk estimation, AI
vendor build by solution estimates,
super complicated work. You can have a
skill for that now. You don't have to
write a gigantic prompt in the same way
you did. You can just say, "Hey, please
assess this vendor." And it will call
the skill. It will be so much more
intuitive. I'm so excited for this. All
right. So, with that in mind, let's
check out that Claude capability screen.
Okay. Here we are. We are looking at the
skills that are in Claude. Now, this is
my Claude and I want to show you that
there are both standard skills and
custom skills here. Standard skills,
you're going to see brand guidelines,
canvas design, MCP builder. These are
all skills that Claude provides for us
as a way of getting this whole ecosystem
started. I created prompting pattern
library and it says so added by me right
59 minutes ago. and it says what it is
and it's basically a file of prompting
best practices so that if I talk about
how I want to create a great prompt, it
will just invoke prompting pattern
library and make that so much easier.
This is super easy to enable. All you
have to do is just enable the skill
section at the top and then enable these
toggles piece by piece down here and
you're done. All right, I want to show
you an actual skill that I'm building.
So, I said, "Claude, can you help me
build a skill for strategizing job
search?" And I want you to note that
this is not the world's best prompt. And
I did that on purpose. I wanted to call
out that it's possible to build a good
skill and it doesn't have to be perfect.
The prompt doesn't have to be perfect.
So, I I just laid out a bunch of things
that I wanted, guidance on how to
interview the user, how to target the
job, etc. And so, Claude then starts to
think about how to create skills. And it
turns out that one of the things that
Enthropic released, which I think is
really smart, is documentation for
Claude on creating skills. So Claude
read the instruction manual for creating
these this skill and then came back and
said, "This is really great. I see this.
I have some questions. Here's some
questions about how I should analyze the
company's news strategies that are most
important, etc." I came back with a
response. I gave it some examples. I had
an LLM help me build some of this and
then said, "Great, excellent details.
I'm going to start building." And so it
has now spent the last five or so
minutes building this skill and it comes
back with a job search strategist zip
file. It's a complete skill done. It's
as easy as that. I can now download this
zip file and re-upload it to Claude in
the capabilities section and I will have
a usable job search strategist skill.
Now, if I want to make it better, which
is always one of the things I focus on,
I always think about how I can evaluate
this skill through the lens of another
LLM. And so, I can take this skill over
to chat GPT and I can say, "Hey, can you
just crack open this zip file, look
inside, and can you assess whether or
not this is high quality and make
specific recommendations for how to
improve it?" And then I can pull that
Chad GPT critique, bring it back into
Claude, and have Claude further improve
the skill. So, I'm not just sitting here
taking what Claude gives me. I'm
actually trying to use a multi LLM
strategy to make this skill as useful as
I possibly can. Now, let's jump over to
chat GPT and I'll show you how I can use
a skill that I developed in Claude for
Claude in Chat GPT. All right, here we
are in chat GPT. You see that I've
uploaded a zip file. This is literally
the exact same zip file that I would
upload if I was in CLA. I am uploading
it per chat because that's how chat GPT
works. And all I say is, "Using this
file, can you help me come up with a
really strong prompt for instructing an
LLM to build a PowerPoint? You'll need
to crack open the file to do so." So, it
opens the file and it immediately comes
up with a very strong PowerPoint. I
don't have to give it all of this. It
reads it in the file. And so, look, I
love the cloud interface. It's very
intuitive for it to call in the skills.
I think that's a lovely touch. But I can
use the exact same files in a chat, GPT
chat, and get a great result. I can use
them in a Gemini chat and get a great
result. And nobody is talking about
that. Nobody is saying that really what
has been invented is a way of working
with AI that gives you composable Lego
bricks. I think that's fantastic. And so
you can just pop this in and all you
have to do is build the ones you want.
And I gave you some of those tips on how
you build them. You literally just say
what you want and work with Claude to
build it. And Claude has the skill
creation. And you could do the same
thing with chat GPT to be honest. You
can say, "I want you to create a
markdown file." The markdown file needs
to be a complete clear set of
instructions to help a LLM accomplish a
very complex task. In addition, please
create these other file types that help
the LLM do the task. If it's an analysis
uh file, you may want to give the LLM
some specific instructions about how to
analyze, etc. And then you put it all
together into a zip file and you're
done. And you have your skill and you
can upload that and say, "Hey, refer to
this skill. This is how I like things
done." You might be wondering now what
things should be skills. What things
should be skills? The answer is quite
simple. If it is something that you
would want to onboard someone with,
let's say you have an employee and you
want to onboard them and train them,
super easy. Just give them a skill.
That's what this is for. That's the
level we're at. If it's a one-off task,
if you're not going to repeat it, if
it's not very high value, don't do a
skill. It's just too much trouble. But
if it's something where it's like, "No,
I'm going to be doing this repeatedly."
If I had someone doing this for me, I
would give them some training. I would
give them some onboarding materials.
That's when you need the skill. And the
beauty of the whole ecosystem is that we
can all just like create the skills and
trade them around and they'll grow. And
I think that that is part of what makes
this so powerful is that it's not locked
into anthropic. People will come up with
ways to use these exact files and other
interfaces. I guarantee that people will
come up with ways to use these exact
same Claude skills folders and files in
a dozen other tools in the next month
because they're so powerful. So, I'm
really excited about this. If you are
asking me what is the catch, where do I
need to be careful? I would tell you
this. We were using the skills before we
knew they existed. So, when I did my
video on Excel, when I did my video on
PowerPoint, Claude was using those
skills. And what I found in practice
weeks ago and since as I've been working
with those tools daily is that even
though the skills are like a massive 10x
step up in helping you get stuff done. I
like watch the video on powerpoints.
Like it creates incredible powerpoints
that save days of work. Like it's a it's
a phenomenal job. You still need to
prompt well. It does not get you away
from prompting well when you do serious
work. Prompting well is like giving this
massive cool skill package clear
direction. And so it doesn't have to be
as long a prompt, but it has to be very
clear and unambiguous about where you
want to take all of this power, all of
this context you've got. So that's if
you want to catch, that's the catch. You
still got to be clear in what you're
asking for, but you don't have to be as
lengthy as you used to have to be. Like
if I had to do a complicated piece of
work like the job search thing, I would
honestly not even do it in one chat. I
would just do it in multiple chats,
right? And you ask for this and then you
ask for this and then you ask for this,
like help me with my resume, help me
with my job search, etc. And you have to
sort of reinvent the prompt and reinvent
the context every time. The power of
this is you can do that much more
complicated work in a much less heavy
lift way. That is why I call them super
prompts because it's like we've taken
this load that we've all had to carry
for prompting for so long and it's like
lifted it. It's like yes, you still have
to be clear. It's good to be clear about
what you want. It's good to bring your
specific context. Bring that specific
job description, right? Bring the
specific experience you have that nobody
else has, right? But you don't have to
carry as heavy a load on just explaining
everything in exhaustive detail as you
used to have to. And that is a huge
breakthrough for all of us. I am so
excited for that. So, I'm putting
together a whole set of Claude skills
that you can use in chat GPT and Gemini.
You can use them in Claude, of course. I
can't wait to show them to you. I'll
have them out with this video on the
substack. It's going to be great. We are
just at the beginning of this and I want
to give you like a great get started
pack so you're off to the races on using
cloud skills. Have fun with your new
super prompting powers.